Title :
Efficient prediction of crosstalk in VLSI interconnections using neural networks
Author_Institution :
Pettit Microelectron. Res. Center, Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
The unique approach proposed for VLSI crosstalk prediction involves the creation of parameterized models of primitive interconnect structures-wirecells-using modular artificial neural networks (MANNs). The finite element method, a circuit simulator and a neural network multi-paradigm prototyping system are coupled together to produce a library of re-usable MANN-based wirecell models
Keywords :
VLSI; circuit simulation; crosstalk; finite element analysis; integrated circuit interconnections; integrated circuit metallisation; integrated circuit modelling; integrated circuit packaging; neural nets; MANNs; VLSI crosstalk prediction; VLSI interconnections; circuit simulator; crosstalk; crosstalk prediction; finite element method; modular artificial neural networks; neural network multi-paradigm prototyping system; neural networks; parameterized models; primitive interconnect structures; re-usable MANN-based wirecell model library; wirecells; Artificial neural networks; Circuit simulation; Coupling circuits; Crosstalk; Finite element methods; Integrated circuit interconnections; Libraries; Predictive models; Very large scale integration; Virtual prototyping;
Conference_Titel :
Electrical Performance of Electronic Packaging, 2000, IEEE Conference on.
Conference_Location :
Scottsdale, AZ
Print_ISBN :
0-7803-6450-3
DOI :
10.1109/EPEP.2000.895499
